© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7271
    Prev
    Next
    INDEX
    Explanations

    statements related to sharing information or shedding light on a subject

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    85
    +0.14
    0.6%
    144
    +0.10
    0.4%
    195
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.14
    0.02
    223
    +0.10
    0.01
    144
    +0.09
    0.01
    Negative Logits
    icians
    -0.78
    ournals
    -0.65
    DragonMagazine
    -0.65
    teness
    -0.63
    ãĥĦ
    -0.60
     appropri
    -0.60
     Rowling
    -0.59
     multiplier
    -0.59
    ICO
    -0.59
    HCR
    -0.58
    POSITIVE LOGITS
     hairs
    0.90
     jaws
    0.87
     light
    0.85
     tears
    0.84
    ibilities
    0.78
    urst
    0.76
    ritten
    0.75
    lighting
    0.74
     sight
    0.74
    iencies
    0.73
    Activations Density 0.023%

    No Known Activations